CASAS Smart Home dataset - scripted activities, separated and interweaved

This dataset represents sensor events collected in the CASAS smart apartment testbed at Washington State University. The data represents participants performing eight iADL (instrumental ADL) activities in the apartment.  The participants first perform each task separately (the data is stored in separate files for each activity) then are asked to perform the entire set of eight activities again in any order, interweaving and performing tasks in parallel as desired (the data is stored in the interwoven file, for 19 of the participants). This resource is valuable for designing and validating activity recognition algorithms for data collected in realistic settings where activities are not always performed completely without interruption.

The eight activities are:

1. Fill medication dispenser.  The participant moves to the kitchen, retrieves a pill dispenser and bottle of pills, and follows directions to fill the dispenser.
2. Watch DVD.  The participant moves to the living room, puts a DVD in the player and watches a news clip on TV.
3. Water plants.  The participant retrieves a watering can from the kitchen supply closet and waters three plants.
4. Answer the phone.  The phone rings and the participant answers it.  The participant converses over the phone with the experimenter to answer some questions about the news clip they watched.
5. Prepare birthday card.  The participant fills out a birthday card with a check to a friend and addresses the envelope.
6. Prepare soup.  The participant moves to the kitchen and prepares a cup of noodle soup in the microwave, following the directions on the package.  The participant brings the soup and a glass of water to the dining room table.
7. Clean.  The participant sweeps the kitchen floor and dusts the living room and dining room using supplies retrieved from the kitchen supply closet.
8. Choose outfit.  The participant selects an outfit from the clothes closet that their friend will wear for a job interview.

The files are named according to the participant number and task number (e.g., p01.t1.csv contains sensor data for participant 1 performing task 1). There is one sensor reading in each row.

A floorplan of the smart apartment is provided in Chinook.png, together with the locations of the sensors. A zoomed-in look at the Chinook cabinet with sensors is provided in Chinook_Cabinet.png. The sensors are categorized (and named) as:

• M01 - M026: PIR motion detectors, reporting ON when detected motion starts and OFF when it stops
• I01 - I08: item use sensors for (in order) oatmeal, raisins, brown sugar, bowl, measuring spoon, medicine container, pot, phone book (present or absent indicating item is on sensor or not)
• D01 - D12: door sensors on cabinets (open or close)
• AD1-A and AD1-B: water sensors for kitchen sink (value indicates level)
• AD1-C: burner sensor (value indicates level)
• P01: phone use sensor
• T01 - T03: temperature sensors